3D OBJECT INTERNAL HOLLOWING FORM LIGHTWEIGHT METHOD BASED ON FUNCTION REPRESENTATION

    公开(公告)号:US20220019704A1

    公开(公告)日:2022-01-20

    申请号:US17258019

    申请日:2020-07-06

    Abstract: The present invention discloses a 3D shape internal hollowing form lightweight method based on function representation, and belongs to the field of computer-aided design. First, function representation is used and effective analytical calculation of shape optimization is explored; then, under the constraint of given external conditions, the stress structure design of a 3D object as well as the problems of center of mass, stand stability, tumbler design and buoyancy of an object are modeled by building an energy function model, and a corresponding discrete computation is given; finally, the above modeling problems are geometrically optimized to obtain an optimized internal shape of the object under given constraint conditions. The present invention greatly shortens the design and optimization cycles of this kind of cavity structures and can give theoretically optimal results.

    Eddy current energy-dissipating spacer

    公开(公告)号:US11223190B2

    公开(公告)日:2022-01-11

    申请号:US16761169

    申请日:2019-02-21

    Abstract: An eddy current energy-dissipating spacer is mainly composed of a spacer frame, a conductor clamp and energy-dissipating elements. The eddy current energy-dissipating spacer not only provides the function of an ordinary spacer, but also reduces the vibration of the transmission lines; and at the same time, can effectively reduce the vibration of the transmission lines, especially the torsional vibration by adopting the eddy current and viscoelastic material for energy dissipation; improves the eddy current strength by adjusting the gear radius ratio, thus increasing the damping force; can adjust the damping parameters by adjusting the magnetic field strength of the permanent magnet; can produce long-term stable vibration reduction effect by adopting the permanent magnet to provide continuous magnetic field without additional external energy input; can effectively avoid the magnetic flux leakage of magnetic circuits by adopting the magnetic material.

    MULTI-CAVITY SUPERIMPOSED NON-RESONANT PHOTOACOUSTIC CELL AND GAS DETECTION SYSTEM

    公开(公告)号:US20210404949A1

    公开(公告)日:2021-12-30

    申请号:US17289658

    申请日:2019-01-30

    Abstract: The present invention belongs to the field of trace gas detection technology and provides a multi-cavity superimposed non-resonant photoacoustic cell and gas detection system. The multi-cavity superimposed non-resonant photoacoustic cell includes a cylindrical metal shell, a plurality of non-resonant photoacoustic cavities, a sensitive diaphragm of the fiber-optic Fabry-Perot acoustic sensor, an optical glass window, an air inlet and an air outlet. The circular sensitive diaphragm of the fiber-optic Fabry-Perot acoustic sensor is fixed on one side of the cylindrical metal shell, and the other side of the cylindrical metal shell is sealed by an optical glass window. The gas to be measured enters through the inlet, diffuses into a plurality of non-resonant photoacoustic cavities, and exits through the outlet on the other side.

    IRON-BASED SUPERALLOY FOR HIGH TEMPERATURE 700 C WITH COHERENT PRECIPITATION OF CUBOIDAL B2 NANOPARTICLES

    公开(公告)号:US20210395869A1

    公开(公告)日:2021-12-23

    申请号:US17343408

    申请日:2021-06-09

    Abstract: An iron-based superalloy for high temperature 700° C. with coherent precipitation of cuboidal B2 nanoparticles, belongs to the field of heat-resistant stainless steel, including Fe, Cr, Ni, Al, Mo, W, Zr, B elements. C, Si, Mn, S, P, O, N are impurity elements. The weight percent (wt. %) of its alloy composition is Cr: 10.0˜12.0, Ni: 13.0˜15.0, Al: 6.0˜7.0, Mo: 2.0˜3.0, W: 0.3˜0.7, Zr: 0.03˜0.05, B: 0.004˜0.007, C≤0.02, Si≤0.20, Mn≤0.20, S≤0.01, P≤0.02, O≤0.005, N≤0.02, Fe: balance; and the atomic percent ratio of Zr/B is 1:1, the atomic percent ratio of Cr/(Mo+W) is 8:1, and the atomic percent ratio of Mo/W is 8:1. The coherent precipitation of cuboidal B2 nanoparticles in ferritic matrix through the alloy composition design.

    UNSUPERVISED CONTENT-PRESERVED DOMAIN ADAPTATION METHOD FOR MULTIPLE CT LUNG TEXTURE RECOGNITION

    公开(公告)号:US20210390686A1

    公开(公告)日:2021-12-16

    申请号:US17112623

    申请日:2020-12-04

    Abstract: The invention discloses an unsupervised content-preserved domain adaptation method for multiple CT lung texture recognition, which belongs to the field of image processing and computer vision. This method enables the deep network model of lung texture recognition trained in advance on one type of CT data (on the source domain), when applied to another CT image (on the target domain), under the premise of only obtaining target domain CT image and not requiring manually label the typical lung texture, the adversarial learning mechanism and the specially designed content consistency network module can be used to fine-tune the deep network model to maintain high performance in lung texture recognition on the target domain. This method not only saves development labor and time costs, but also is easy to implement and has high practicability.

    DEPTH ESTIMATION AND COLOR CORRECTION METHOD FOR MONOCULAR UNDERWATER IMAGES BASED ON DEEP NEURAL NETWORK

    公开(公告)号:US20210390339A1

    公开(公告)日:2021-12-16

    申请号:US17112499

    申请日:2020-12-04

    Abstract: The invention discloses a depth estimation and color correction method for monocular underwater images based on deep neural network, which belongs to the field of image processing and computer vision. The framework consists of two parts: style transfer subnetwork and task subnetwork. The style transfer subnetwork is constructed based on generative adversarial network, which is used to transfer the apparent information of underwater images to land images and obtain abundant and effective synthetic labeled data, while the task subnetwork combines the underwater depth estimation and color correction tasks with the stack network structure, carries out collaborative learning to improve their respective accuracies, and reduces the gap between the synthetic underwater image and the real underwater image through the domain adaptation strategy, so as to improve the network's ability to process the real underwater image.

    DEEP NETWORK LUNG TEXTURE RECOGNITON METHOD COMBINED WITH MULTI-SCALE ATTENTION

    公开(公告)号:US20210390338A1

    公开(公告)日:2021-12-16

    申请号:US17112367

    申请日:2020-12-04

    Abstract: The invention discloses a deep network lung texture recognition method combined with multi-scale attention, which belongs to the field of image processing and computer vision. In order to accurately recognize the typical texture of diffuse lung disease in computed tomography (CT) images of the lung, a unique attention mechanism module and multi-scale feature fusion module were designed to construct a deep convolutional neural network combing multi-scale and attention, which achieves high-precision automatic recognition of typical textures of diffuse lung diseases. In addition, the proposed network structure is clear, easy to construct, and easy to implement.

    Fully automatic natural image matting method

    公开(公告)号:US11195044B2

    公开(公告)日:2021-12-07

    申请号:US16963140

    申请日:2020-05-13

    Abstract: The invention belongs to the field of computer vision technology, and provides a fully automatic natural image matting method. For image matting of a single image, it is mainly composed of the extraction of high-level semantic features and low-level structural features, the filtering of pyramid features, the extraction of spatial structure information, and the late optimization of the discriminator network. The invention can generate accurate alpha matte without any auxiliary information, saving the time for scientific researchers to mark auxiliary information and the interaction time when users use it.

    HYBRID DYNAMICALLY INSTALLED ANCHOR WITH A FOLDING SHANK AND CONTROL METHOD FOR KEEP ANCHOR VERTICALITY DURING FREE FALL IN WATER

    公开(公告)号:US20210362810A1

    公开(公告)日:2021-11-25

    申请号:US17260128

    申请日:2020-02-17

    Abstract: The present invention relates to a hybrid dynamically installed anchor with a folding shank and a control method to keep the verticality of the hybrid anchor during free fall in the seawater, which can be applied to the field of offshore engineering. The hybrid anchor comprises a folding-shank plate anchor, a ballast shaft, an extension rod, a plurality of rear fins, and a recovery hole from the front to the tail. The folding shank is not only useful in reducing the water and soil resistance during installation, but also beneficial in improving the directional stability of the hybrid anchor during free fall in the seawater. The re-used shaft can significantly increase the penetration depth of the folding-shank plate anchor and reduce the installation cost at the same time. The control method keeping the verticality of the hybrid anchor can improve the success rate during anchor installation.

    Helical Milling Tool with Forward-Backward Feeding

    公开(公告)号:US20210362248A1

    公开(公告)日:2021-11-25

    申请号:US17053044

    申请日:2018-05-04

    Abstract: Disclosed is a helical milling tool with forward-backward feeding, the tool including a cutting portion, a neck portion and a handle portion, which are successively connected to each other; wherein the cutting portion includes a front-end cutting section, a circumferential cutting section and a back-end cutting section, which are connected successively to each other; the front-end cutting section is of an end milling cutter structure or a drill bit structure; the circumferential cutting section is of a cylindrical shape and is of a circumferential milling cutter structure; and the back-end cutting section is of a frustum-shaped. The tool can avoid defects such as layering and tearing, which go beyond processing requirements in a composite material, improve the processing quality, save on costs, simplify the processing process, improve the production efficiency and prolong the service life of the tool.

Patent Agency Ranking